CN113208575A

CN113208575A - Method and system for detecting coronavirus infection by using wearable device of Internet of things

Info

Publication number: CN113208575A
Application number: CN202110487735.1A
Authority: CN
Inventors: 周克明; 张洪滔; 胡豁生
Original assignee: Chengdu Anrui Health Technology Co ltd
Current assignee: Chengdu Anrui Health Technology Co ltd
Priority date: 2021-05-06
Filing date: 2021-05-06
Publication date: 2021-08-06

Abstract

A method and a system for detecting coronavirus infection by using an Internet of things wearable device relate to the field of medical health. The method comprises the following steps: s1, the wearable device of the Internet of things collects the coronavirus clinical symptom data of the device wearer through a sensor; s2, the wearable device of the Internet of things uploads the clinical symptom data to a remote data processing device of the Internet of things through a network or a communication protocol; s3, after receiving the clinical symptom data, the Internet of things remote data processing device respectively performs sampling, filtering and classification detection on the clinical symptom data; s4, the remote data processing device of the Internet of things performs data fusion on the processing result of the clinical symptom data; and S5, directly classifying the fused data by using a threshold rule or a machine learning algorithm, and judging the detection result. The invention effectively detects early clinical symptoms of coronavirus infection by using wearable sensing equipment.

Description

Method and system for detecting coronavirus infection by using wearable device of Internet of things

Technical Field

The present invention relates to the field of medical health.

Background

The new coronavirus Covid-19 has brought fatal threat to the world economy and human life, and simultaneously brings great pressure and challenge to the medical system of each country in the world. According to the recommendation of the world health organization, high fever, continuous cough and dyspnea are typical clinical symptoms of the new coronavirus Covid-19, and timely and accurate diagnosis through the clinical symptoms has great clinical significance for effectively preventing the spread of the coronavirus. The existing method for monitoring the new coronavirus is RT-PCR and isothermal nucleic acid amplification detection method, but the method is expensive and is difficult to detect and screen everyone. The relatively low cost antibody detection does not allow an early confirmation of whether the patient carries a coronavirus, and a positive antibody detection only identifies that the carrier has recovered or is in the recovery stage of a coronavirus infection.

Disclosure of Invention

One of the purposes of the invention is to provide a method for detecting coronavirus infection by using an internet-of-things wearable device, which can effectively detect early clinical symptoms of coronavirus infection.

Another object of the present invention is to provide a system for detecting coronavirus infection by using a wearable device of internet of things, which can effectively detect early clinical symptoms of coronavirus infection.

The purpose of the invention can be realized by designing a method for detecting coronavirus infection by using an internet-of-things wearable device, which comprises the following steps:

s1, the wearable device of the Internet of things finishes the collection of coronavirus clinical symptom data of a wearer of the wearable device of the Internet of things through a sensor, wherein the clinical symptom data comprise body temperature, blood oxygen, respiration rate and cough data;

s2, the wearable device of the Internet of things uploads the clinical symptom data to a remote data processing device of the Internet of things through a mobile communication network or a communication protocol;

s3, after receiving the clinical symptom data sent by the wearable device of the Internet of things, the remote data processing device of the Internet of things carries out sampling, filtering and classification detection on the clinical symptom data respectively;

s4, the remote data processing device of the Internet of things performs data fusion on the processing result of the clinical symptom data;

and S5, directly classifying the fused data by using a threshold rule or a machine learning algorithm, and judging the detection result.

Further, when the remote data processing device of the internet of things is a mobile phone, the method further includes step S6: if the detection is successful, the mobile phone APP reports the result to the Audar intelligent Internet of things server through the network, the Audar intelligent Internet of things server is communicated with the disease control department, and the Audar intelligent Internet of things server reports the result to the disease control department.

Further, the sensors comprise a blood vessel volume map sensor, an electrocardio sensor, a temperature sensor and a microphone, and the sensors finish the collection of the coronavirus clinical symptom data of the wearable device wearer of the Internet of things.

Further, in step S3, the sampling is a periodic sampling; filtering to remove noise; the classification detection is processed by a corresponding classifier, and the classifier is a classifier of fuzzy logic plus a threshold value or a classifier based on machine learning; the temperature data is analyzed and judged by the classifier I to determine whether the body temperature is too high; analyzing and processing the blood oxygen and respiration rate data by using a classifier II, and judging whether abnormal features appear; the audio data is analyzed and processed by a classifier III to judge whether the wearer has cough symptoms.

Further, after the classifier I, the classifier II and the classifier III judge the corresponding input data into a positive class, the positive class is continuously input into the classifier IV for further processing, so that whether the wearer has early symptoms of the new coronavirus is directly judged through a threshold value or judged by using a classifier based on machine learning; for machine learning based classifiers, training with data is required.

Further, the data fusion in step S4 adopts a fuzzy logic algorithm, completes the data fusion through fuzzification, rule application and defuzzification, and the fuzzy logic fuses a plurality of input data into one data output.

Further, the threshold rule in step S5 is to compare the output of the fuzzy logic with a preset threshold; the machine learning is to process data by adopting algorithms, wherein the algorithms comprise an artificial neural network method, a decision tree method, a support vector machine, a weighted average method and a multi-Bayes estimation method

The other purpose of the invention can be realized by designing a system for detecting coronavirus infection by using an internet-of-things wearable device, which comprises the internet-of-things wearable device and an internet-of-things remote data processing device; the wearable device of the Internet of things is an intelligent watch or an intelligent bracelet or an intelligent device which can be embedded into shoes, hats, clothes and trousers; the remote data processing device of the Internet of things is a cloud data processing server or a mobile phone;

the wearable device of the Internet of things comprises a micro-control unit, a temperature sensor, a blood oxygen and respiration rate measuring unit, a sound collecting sensor, an input unit, a display module, an output unit and a wrist strap device communication module;

the cloud data processing server comprises a processing engine, an information database and a server communication module; the processing engine finishes deploying the classifier I, the classifier II, the classifier III and the classifier IV; the information database stores the clinical data of the wearer; the server communication module exchanges data with the wearable device of the Internet of things through a communication network;

the mobile phone comprises a processing engine, a collection end database and a mobile phone communication module; the processing engine finishes deploying the classifier I, the classifier II, the classifier III and the classifier IV; a collection end database and a machine learning model are stored; the mobile phone communication module exchanges data with the wearable device of the Internet of things through a communication network or a communication protocol.

Furthermore, the micro control unit sends instructions to the sensor and other input and output units, analyzes the received data and outputs the result through the display and output module;

the temperature sensor is used for collecting body temperature data of a wearer and transmitting the body temperature data to the micro control unit;

the blood oxygen and respiration rate measuring unit adopts a blood vessel volume map sensor and/or an electrocardio sensor; transmitting blood oxygen and respiration rate data to a micro control unit;

a sound collection sensor, which adopts a microphone; collecting the sound data of the wearer and transmitting the sound data to the micro-control unit;

an input unit comprising a mechanical key and/or a touch screen or a microphone; inputting an instruction to the micro control unit;

the display module adopts an LCD/OLED display screen and/or an LED lamp to display information;

the output unit is a loudspeaker and/or a vibration motor; the micro control unit alarms after finding abnormality;

the wrist strap device communication module is a mobile communication module and/or a communication protocol module and uploads data to the remote data processing device of the Internet of things.

Furthermore, the cloud data processing server also comprises an external communication interface, and the external communication interface is a disease control communication interface; the mobile phone also comprises a communication interface which is used for finishing communication with the server side server.

The invention effectively detects early clinical symptoms of coronavirus infection by using low-cost wearable sensing equipment, and realizes detection of vital sign data such as body temperature, blood oxygen, respiration rate, cough and the like. The physiological health state of the user can be monitored in real time by the user, so that epidemic diseases are prevented from being infected, and the risk of virus infection is reduced. The wearable intelligent sensor and the artificial intelligence are combined to provide public health management service so as to resist the spread of epidemic diseases such as coronavirus in people.

Drawings

FIG. 1 is a flow chart of remote processing in accordance with the preferred embodiment of the present invention;

FIG. 2 is a flow chart of the fuzzy logic process of the preferred embodiment of the present invention;

FIG. 3 is a graph of membership of a portion of clinical symptom data in accordance with a preferred embodiment of the invention;

FIG. 4 is a schematic view of a preferred embodiment of the present invention;

fig. 5 is a schematic diagram of an internet of things wearable device according to a preferred embodiment of the invention;

FIG. 6 is a diagram illustrating a cloud data processing server according to a preferred embodiment of the present invention;

FIG. 7 is a schematic diagram of a mobile phone according to a preferred embodiment of the present invention.

Detailed Description

The present invention will be further described with reference to the following examples.

As shown in fig. 1 and 2, a method for detecting coronavirus infection by using an internet-of-things wearable device includes the following steps:

s1, the wearable device of the Internet of things finishes the collection of the coronavirus clinical symptom data of the wearable device wearer of the Internet of things through the sensor, and the clinical symptom data comprise body temperature, blood oxygen, respiration rate and cough data.

The sensors comprise a blood vessel volume map (PPG) sensor, an Electrocardiogram (ECG) sensor, a temperature sensor and a microphone, and the sensors complete the collection of the coronavirus clinical symptom data of the wearable device wearer of the Internet of things through a fusion algorithm.

In an embodiment, the PPG and ECG may employ AS7030 of AMS, PAH8112ES in pristine, MAX30101, MAX30001 of Maxim. The temperature sensor may use Maxim's MAX 30208. The microphone can be a microphone of a mobile phone or a watch.

And S2, the wearable device of the Internet of things uploads the clinical symptom data to a remote data processing device of the Internet of things through a mobile communication network or a communication protocol.

And S3, after receiving the clinical symptom data sent by the wearable device of the Internet of things, the remote data processing device of the Internet of things carries out sampling, filtering and classification detection on the clinical symptom data respectively.

In step S3, the sampling is a periodic sampling; filtering to remove noise; the classification detection is processed by a corresponding classifier, and the classifier is a classifier of fuzzy logic plus a threshold value or a classifier based on machine learning; the temperature data is analyzed and judged by the classifier I to determine whether the body temperature is too high; analyzing and processing the blood oxygen and respiration rate data by using a classifier II, and judging whether abnormal features appear; the audio data is analyzed and processed by a classifier III to judge whether the wearer has cough symptoms.

Any sensor can generate white Gaussian noise during working, so that noise appears in audio, blood oxygen and temperature, and filtering and noise removal are needed.

Besides fuzzy logic, the fusion algorithm also comprises a weighted average method, a multi-Bayesian estimation method, an artificial neural network method and the like.

Classifier i is a temperature classifier that uses a temperature threshold of 37 to 37.5 degrees for classification. In this example, a temperature threshold of 37.5 degrees is used by classifier I.

The classifier II is a blood oxygen and respiration rate classifier, a second threshold value can be added through a fusion algorithm, the output after fusion is a range, and the range can be normalized to an interval of 0 to 1, and 0.5 is set as the second threshold value in the embodiment; or directly using a machine learning method to train a classifier to directly classify the data. In this embodiment, the machine learning adopts a supervised learning method, and blood oxygen and respiration rate data (or simulated data) of a patient and blood oxygen and respiration rate data of a normal person are collected and sent to a machine learning model for training. The trained classifier can be used directly.

The classifier III is a cough symptom classifier and can be used for directly judging by using a sound threshold value or judging by using a neural network to identify the size, the frequency and the like of the cough characteristic comprehensive cough. In this embodiment, the sound threshold is set to 30, and after removing the ambient noise and other sounds, the cough volume exceeds 30 db, and it is considered that there is a symptom.

And S4, the remote data processing device of the Internet of things performs data fusion on the processing result of the clinical symptom data.

After judging the corresponding input data into a positive category, the classifier I, the classifier II and the classifier III continue to input the positive category into the classifier IV for further processing, so that the judgment of whether the wearer has early symptoms of the new coronavirus is directly carried out through a threshold value or is carried out by using a classifier based on machine learning; for machine learning based classifiers, training with data is required.

The classifier IV is a comprehensive classifier. The comprehensive classifier can also have two schemes, the first scheme is that a fusion algorithm is added with a comprehensive threshold value, the output range is controlled to be 0 to 1 after fusion and normalization, and 0.5 is taken as the comprehensive threshold value in the embodiment. The second is to train the classifier directly by machine learning. In this embodiment, the machine learning is a supervised learning method, and data of the patient, including one or more of body temperature, respiration rate, (cough) sound, blood oxygen concentration, (these data may also be simulated data), and the above data of the normal person, are sent to the machine learning model for training. The trained classifier can be used directly.

The data fusion in the step S4 adopts a fuzzy logic algorithm, completes the data fusion through fuzzification, rule application and defuzzification, and fuzzy logic fuses a plurality of input data into one data to be output.

For example, the range of blood oxygen concentration 90% to 100% and respiratory rate 10 to 50 (times/minute) is first normalized to the range of 0 to 1, and the two inputs are classified as low, medium or high, as shown in Table 1. The normalization method comprises the following steps: (max-value)/(max-min). For example, the blood oxygen concentration is 95% (1-0.95)/(1-0.9) ═ 0.5, and the blood oxygen is less than 90%, and is calculated as 0. The respiration rate can also be calculated using this formula, less than 10 to 0 and more than 50 to 1.

Table 1: fuzzy classification

Input device	Low (L)	Middle (M)	High (H)
				Input 1 (blood oxygen concentration)	0-0.2	>0.2-0.6	0.6-1
Input 2 (respiration rate)	0-0.2	>0.2-0.6	0.6-1

A decision matrix for fuzzy logic is then created based on the two input categories in Table 1, as shown in Table 2 below

Output of	Input 1 ═ L	Input	2 ═ M	Input	2 ═ H
						Input
2 ═ L	L	M	M
				Input
2 ═ M	M	H	H
				Input
2 ═ H	M	H	H

For example, according to the decision matrix, if input 1 is medium and input 2 is also medium, the total fuzzy logic output is high, and then 1 is output (logic yes). According to the table above, an alarm is not triggered when one of the two inputs is low.

Those skilled in the art will appreciate that tables 1 and 2 present simple examples of fuzzy logic, however, fuzzy logic may have more inputs and the classification of the inputs and the decision matrix itself may be more complex.

As shown in fig. 3, the fuzzy system includes two processes: fuzzification and defuzzification. The blurring itself comprises two processes: and calculating the membership degree and the application rule.

In this embodiment, the calculation of the degree of membership is shown in FIG. 4, where FIG. 4 defines how to calculate the low, medium, and high degrees of membership for each input. For example, when the temperature T is 0.2, T (low) is 0, T (medium) is 1, and T (high) is 0, and when T is 0.8, T (low) is 0, T (medium) is 0, and T (high) is 0.6.

Once the degree of membership is obtained, the rules may be applied. Table 3 provides exemplary rules. The low, medium, and high Output Weights (OW) may be set between 0 and 1. As shown in table 3, the refractory strength (FS) uses a minimum degree of membership of 4 inputs. For example, for rule 9, if T (high) is 0.1, RR (medium) is 0.2, SpO2 (low) is 0.3, and sound volume (low) is 0.3, FS9 is min (0.1,0.2,0.3,0.3) is 0.1.

Defuzzification uses the following formula:

in the formula: output is Output after defuzzification, FS_iFor fire resistance, OW_iIs the output weight.

The output after defuzzification ranges from 0 to 1 and can be characterized by a probability of symptoms.

TABLE 3

The threshold rule in step S5 is to compare the output of the fuzzy logic with a preset threshold; machine learning is the processing of data by algorithms including neural networks, decision trees, and support vector machines. Besides fuzzy logic, there are weighted average method, multi-Bayes estimation method, artificial neural network method, etc. The machine learning adopts a supervised learning method, collects data of patients (or simulated data) and data of normal persons, and sends the data into a machine learning model for training. The trained classifier can be used directly.

Taking the algorithm of the neural network as an example, a three-layer fully-connected neural network is designed, the first layer comprises 4 neurons, and each neuron corresponds to an input, namely temperature, blood oxygen, respiration rate and sound signals. The second layer is 2 neurons, and the third layer is 1 neuron. Each neuron of the first layer and the second layer comprises a nonlinear function of RELU, the neuron of the third layer uses a Sigmoid function to carry out normalization, the output is lower than 0.5, the judgment is logical negation, and the judgment is that the neuron is not infected; a logical YES determination of 0.5 or more indicates that the infection is detected.

It will be appreciated by those skilled in the art that the neural network is merely a simple example and that the structure of the neural network may be more complex.

When the remote data processing device of the internet of things is a mobile phone, the method further comprises the step S6: if the detection is successful, the mobile phone APP reports the result to the Audar intelligent Internet of things server through the network, the Audar intelligent Internet of things server is communicated with the disease control department, and the Audar intelligent Internet of things server reports the result to the disease control department.

The method comprises the steps that an APP is detected through an internet-of-things wearable device and a cloud data processing server/mobile phone end artificial intelligence. The wearable device of thing networking accomplishes the data detection of coronavirus clinical symptom through the sensor that has algorithm fusion, including body temperature, blood oxygen, respiratory rate, four kinds of data of cough, then upload data to data processing server or upload to cell-phone APP through the bluetooth through removing cellular communication.

A coronavirus detection algorithm and a coronavirus detection model are deployed in a cloud data processing server or a mobile phone end artificial intelligence detection APP. After receiving body temperature, blood oxygen, respiratory rate, the cough data that the wearable device of thing networking sent, APP at first carries out sampling, filtering, classification detection respectively to four kinds of data, then carries out data fusion with the processing result, and application fuzzy logic and machine learning algorithm judge the testing result.

The framework has the advantages that the artificial intelligence detection algorithm is deployed to the mobile phone end, the dependence on computing resources of the wearable device of the Internet of things is reduced, the standby time of the wrist strap device is prolonged, and the portability, reliability and stability of the equipment are improved.

As shown in fig. 1, the artificial intelligence detection process of the mobile phone APP end is as follows:

the temperature data is analyzed and judged by the classifier I to determine whether the body temperature is too high;

analyzing and processing the blood oxygen and respiration rate data by using a classifier II, and judging whether abnormal features appear;

the audio data is analyzed and processed by a classifier III to judge whether the wearer has cough symptoms;

after judging the corresponding input data into a positive type by the classifier I, the classifier II and the classifier III, continuously inputting the positive type into the classifier IV for further processing, thereby judging whether the wearer has early symptoms of the new coronavirus;

if the detection is successful, the mobile phone APP reports the result to the Audar intelligent Internet of things server through networks such as 4G and 5G, WIFI, the Audar intelligent Internet of things server can be communicated with a disease control department, and then the result is reported to the disease control department;

the four classifiers are realized by adopting a fuzzy logic model and a machine learning model (such as a neural network, a decision tree, a support vector machine and the like).

As shown in fig. 4 and 5, a system for detecting coronavirus infection by using an internet of things wearable device includes an internet of things wearable device 1 and an internet of things remote data processing device 2; the wearable device of the Internet of things is an intelligent watch or an intelligent bracelet or an intelligent device which can be embedded into shoes, hats, clothes and trousers; the remote data processing device 2 of the internet of things is a cloud data processing server 21 and/or a mobile phone 22.

The wearable device 1 of the internet of things comprises a micro control unit 11, a temperature sensor 12, a blood oxygen and respiration rate measuring unit 13, a sound collecting sensor 14, an input unit 15, a display module 16, an output unit 17 and a wearable device communication module 18, as shown in fig. 5.

As shown in fig. 6, the cloud data processing server 21 includes a server processing engine 211, an information database 212, and a server communication module 213; the server processing engine 211 finishes deploying the classifier I, the classifier II, the classifier III and the classifier IV; the information database 212 stores wearer clinical data; the server communication module 213 exchanges data with the internet of things wearable device 1 through a communication network.

As shown in fig. 7, the mobile phone 22 includes a mobile phone processing engine 221, a collector database 222, and a mobile phone communication module 223; the mobile phone processing engine 221 completes the deployment of a classifier I, a classifier II, a classifier III and a classifier IV; a collector database 222, machine learning model storage; the mobile phone communication module 223 exchanges data with the internet-of-things wearable device 1 through a communication network or a communication protocol.

Wearable device 1 of thing networking is the intelligent wrist-watch or intelligent bracelet for the first choice, and secondly is the equipment or the device that can imbed shoes cap coat and trousers.

And the micro control unit 11 is used for sending instructions to the sensor, the input unit and the output unit, analyzing the received data and outputting the result through the display module and the output module.

And the temperature sensor 12 collects the body temperature data of the wearer and transmits the body temperature data to the micro control unit 11.

A blood oxygen and respiration rate measuring unit 13 which transmits blood oxygen and respiration rate data to the micro control unit 11; both data can be obtained with the same sensor, using a plethysmogram (PPG) sensor and/or an Electrocardiogram (ECG) sensor.

A sound collection sensor 14 using a microphone; the wearer's voice data is collected and transmitted to the micro control unit 11.

An input unit 15 comprising mechanical keys and/or a touch screen or microphone; an instruction is input to the micro control unit 11.

The display module 16, which uses LCD/OLED display screen and/or LED lamp, displays information.

An output unit 17, which is a microphone and/or a vibration motor; the micro control unit 11 outputs an alarm after finding the abnormality.

The wearable device communication module 18 is a mobile communication module and/or a communication protocol module, and uploads data to the remote data processing device 2 of the internet of things. In this embodiment, the bluetooth transmission module and/or the cellular network communication module.

The cloud data processing server 21 further comprises an external communication interface, and the external communication interface is a disease control communication interface; handset 22 also includes a communication interface that completes communication with the server-side server.

In the embodiment, Nordic nRF9160 is used AS the MCU, the NB-IoT and LTE-M communication module and the GPS module are integrated, and AS7030 of the AMS is used AS the PPG and ECG sensors.

Claims

1. A method for detecting coronavirus infection by using an Internet of things wearable device is characterized by comprising the following steps:

2. The method for detecting coronavirus infection by using the wearable device in the internet of things according to claim 1, wherein when the remote data processing device in the internet of things is a mobile phone, the method further comprises step S6: if the detection is successful, the mobile phone APP reports the result to the intelligent Internet of things server through the network, the intelligent Internet of things server is communicated with the disease control department, and the intelligent Internet of things server reports the result to the disease control department.

3. The method for detecting coronavirus infection by using the wearable device of the internet of things as claimed in claim 1, wherein: the sensors comprise a blood vessel volume map sensor, an electrocardio sensor, a temperature sensor and a microphone, and the sensors finish the collection of the coronavirus clinical symptom data of the wearable device wearer of the Internet of things.

4. The method for detecting coronavirus infection by using the wearable device of the internet of things as claimed in claim 1, wherein: in step S3, the sampling is a periodic sampling; filtering to remove noise; the classification detection is processed by a corresponding classifier, and the classifier is a classifier of fuzzy logic plus a threshold value or a classifier based on machine learning; the temperature data is analyzed and judged by the classifier I to determine whether the body temperature is too high; analyzing and processing the blood oxygen and respiration rate data by using a classifier II, and judging whether abnormal features appear; the audio data is analyzed and processed by a classifier III to judge whether the wearer has cough symptoms.

5. The method for detecting coronavirus infection by using the wearable device of the internet of things as claimed in claim 1, wherein: after judging the corresponding input data into a positive category, the classifier I, the classifier II and the classifier III continue to input the positive category into the classifier IV for further processing, so that the judgment of whether the wearer has early symptoms of the new coronavirus is directly carried out through a threshold value or is carried out by using a classifier based on machine learning; for machine learning based classifiers, training with data is required.

6. The method for detecting coronavirus infection by using the wearable device of the internet of things as claimed in claim 1, wherein: the data fusion in the step S4 adopts a fuzzy logic algorithm, completes the data fusion through fuzzification, rule application and defuzzification, and fuzzy logic fuses a plurality of input data into one data to be output.

7. The method for detecting coronavirus infection by using the wearable device of the internet of things as claimed in claim 1, wherein: the threshold rule in step S5 is to compare the output of the fuzzy logic with a preset threshold; the machine learning is to process data by adopting an algorithm, and the algorithm comprises an artificial neural network method, a decision tree method, a support vector machine, a weighted average method and a multi-Bayes estimation method.

8. The utility model provides an utilize wearable device of thing networking to detect system of coronavirus infection which characterized in that: the system comprises an Internet of things wearable device and an Internet of things remote data processing device; the wearable device of the Internet of things is an intelligent watch or an intelligent bracelet or an intelligent device which can be embedded into shoes, hats, clothes and trousers; the remote data processing device of the Internet of things is a cloud data processing server and/or a mobile phone;

the wearable device of the Internet of things comprises a micro-control unit, a temperature sensor, a blood oxygen and respiration rate measuring unit, a sound collecting sensor, an input unit, a display module, an output unit and a wearable device communication module;

the cloud data processing server comprises a server processing engine, an information database and a server communication module; the server processing engine finishes deploying the classifier I, the classifier II, the classifier III and the classifier IV; the information database stores the clinical data of the wearer; the server communication module exchanges data with the wearable device of the Internet of things through a communication network;

the mobile phone comprises a mobile phone processing engine, a collection end database and a mobile phone communication module; the mobile phone processing engine finishes deploying the classifier I, the classifier II, the classifier III and the classifier IV; a collection end database and a machine learning model are stored; the mobile phone communication module exchanges data with the wearable device of the Internet of things through a communication network or a communication protocol.

9. The system for detecting coronavirus infection with an internet-of-things wearable device according to claim 8, wherein:

the micro control unit sends instructions to the sensor and other input and output units, analyzes the received data and outputs the result through the display and output module;

and the wearable device communication module is a mobile communication module and/or a communication protocol module and uploads data to the remote data processing device of the Internet of things.

10. The system for detecting coronavirus infection with an internet-of-things wearable device of claim 8, wherein: the cloud data processing server also comprises an external communication interface, and the external communication interface is a disease control communication interface; the mobile phone also comprises a communication interface which is used for finishing communication with the server side server.